Separation of Concerns for Privacy-Preserving LLM Adoption: A Banking Architecture Framework
Authors’ abstract
Banking employees using third-party Large Language Models risk inadvertently exposing sensitive customer data through prompts. Existing cryptographic solutions impose prohibitive computational costs unsuitable for real-time applications. We present the Bank- ing Prompt Privacy Detector (BPPD), a modular framework im- plementing Separation of Concerns through three components: a locally-hosted DetectorLLM for privacy risk assessment, Format- Preserving Encryption maintaining semantic integrity, and a proxy mediating external LLM interactions. The DetectorLLM adapts Llama-3.2-3B-Instruct through parameter- efficient fine-tuning (LoRA and selective freezing) on 4,170 syn- thetically generated banking scenarios, avoiding exposure of real sensitive data. Evaluation on 1,668 test samples demonstrates sub- stantial improvements over baseline: safety classification accuracy increases from 73.6% to 99.9%, multi-label Subset Accuracy im- proves from 30.5% to 98.5%, and Privacy Hiding Rate rises from 14.4% to 87.3%. The framework enables incremental deployment on commodity hardware (single GPU), providing financial institutions a practical solution for LLM adoption while maintaining GDPR, PCI DSS, and Basel III compliance.
Paper
- Authors
- Y. Kong, S. Bartolucci, F. Caccioli, G. Destefanis
- Publication date
- 2026
Transcript
A transcript has not been published for this episode yet.
Licensing
- Source license
- Creative Commons Attribution 4.0 International
- Recording license
- CC-BY-4.0
The authors and publisher do not sponsor or endorse this recording.